{"id":"https://openalex.org/W4361275685","doi":"https://doi.org/10.3389/fdata.2023.1077318","title":"The detection and effect of social events on Wikipedia data-set for studying human preferences","display_name":"The detection and effect of social events on Wikipedia data-set for studying human preferences","publication_year":2023,"publication_date":"2023-03-30","ids":{"openalex":"https://openalex.org/W4361275685","doi":"https://doi.org/10.3389/fdata.2023.1077318","pmid":"https://pubmed.ncbi.nlm.nih.gov/37063484"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2023.1077318","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3389/fdata.2023.1077318","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2023.1077318/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2023.1077318/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056587453","display_name":"Julien Assuied","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142324","display_name":"CY Cergy Paris Universit\u00e9","ror":"https://ror.org/043htjv09","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142324"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julien Assuied","raw_affiliation_strings":["CY-Tech Cergy Paris Universit\u00e9, Cergy, France"],"affiliations":[{"raw_affiliation_string":"CY-Tech Cergy Paris Universit\u00e9, Cergy, France","institution_ids":["https://openalex.org/I4210142324"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056116368","display_name":"Y\u00e9rali Gandica","orcid":"https://orcid.org/0000-0002-6262-1801"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2802026069","display_name":"Valencian International University","ror":"https://ror.org/00gjj5n39","country_code":"ES","type":"education","lineage":["https://openalex.org/I2802026069"]},{"id":"https://openalex.org/I4210109170","display_name":"Laboratoire de Physique Th\u00e9orique","ror":"https://ror.org/01w0hda30","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I196454796","https://openalex.org/I4210098836","https://openalex.org/I4210109170","https://openalex.org/I4388446414","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210142324","display_name":"CY Cergy Paris Universit\u00e9","ror":"https://ror.org/043htjv09","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210142324"]},{"id":"https://openalex.org/I4387153379","display_name":"Laboratoire de Physique Th\u00e9orique et Mod\u00e9lisation","ror":"https://ror.org/05nhcdk38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210142324","https://openalex.org/I4387153379"]}],"countries":["ES","FR"],"is_corresponding":true,"raw_author_name":"Y\u00e9rali Gandica","raw_affiliation_strings":["CY Cergy Paris Universite, CNRS, Laboratoire de Physique Th\u00e9orique et Modelisation, Cergy, France","Department of Mathematics & Master in Big Data, Universidad Internacional de Valencia (VIU), Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"CY Cergy Paris Universite, CNRS, Laboratoire de Physique Th\u00e9orique et Modelisation, Cergy, France","institution_ids":["https://openalex.org/I4210142324","https://openalex.org/I4210109170","https://openalex.org/I1294671590","https://openalex.org/I4387153379"]},{"raw_affiliation_string":"Department of Mathematics & Master in Big Data, Universidad Internacional de Valencia (VIU), Valencia, Spain","institution_ids":["https://openalex.org/I2802026069"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056116368"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802026069","https://openalex.org/I4210109170","https://openalex.org/I4210142324","https://openalex.org/I4387153379"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04692992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"1077318","last_page":"1077318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9648000001907349,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.8278160691261292},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.7040486335754395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5944353938102722},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5867261290550232},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.5213823914527893},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4609563648700714},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4235779345035553},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4164397120475769},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37620431184768677},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3623185157775879},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3566083312034607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2911570072174072},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24114733934402466}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.8278160691261292},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.7040486335754395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5944353938102722},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5867261290550232},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.5213823914527893},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4609563648700714},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4235779345035553},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4164397120475769},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37620431184768677},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3623185157775879},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3566083312034607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2911570072174072},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24114733934402466},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/fdata.2023.1077318","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3389/fdata.2023.1077318","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2023.1077318/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},{"id":"pmid:37063484","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37063484","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in big data","raw_type":null},{"id":"pmh:oai:HAL:hal-04742955v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04742955","pdf_url":"https://hal.science/hal-04742955/document","source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Big Data, 2023, 6, ⟨10.3389/fdata.2023.1077318⟩","raw_type":"Journal articles"},{"id":"pmh:oai:pubmedcentral.nih.gov:10098102","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10098102","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10098102/pdf/fdata-06-1077318.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Big Data","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:33688635f98e4298b3550dd983deb56b","is_oa":true,"landing_page_url":"https://doaj.org/article/33688635f98e4298b3550dd983deb56b","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Big Data, Vol 6 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fdata.2023.1077318","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3389/fdata.2023.1077318","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2023.1077318/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8579844064","display_name":null,"funder_award_id":"TAP-DD2016","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G966041925","display_name":null,"funder_award_id":"2016-147 ANR OPLADYN TAP-DD2016","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4361275685.pdf"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2048430744","https://openalex.org/W2294870850","https://openalex.org/W2585105539","https://openalex.org/W2743183319","https://openalex.org/W2803565256","https://openalex.org/W2963283515","https://openalex.org/W3047139001","https://openalex.org/W3097570755","https://openalex.org/W6706326074"],"related_works":["https://openalex.org/W2560936962","https://openalex.org/W2788727012","https://openalex.org/W4388203630","https://openalex.org/W2526386912","https://openalex.org/W4390662392","https://openalex.org/W71955863","https://openalex.org/W2359185137","https://openalex.org/W2610918223","https://openalex.org/W2085200861","https://openalex.org/W2789383625"],"abstract_inverted_index":{"Several":[0],"studies":[1,16],"have":[2],"used":[3],"Wikipedia":[4,150,158],"(WP)":[5],"data-set":[6,99,159],"to":[7,22,85,121,164],"analyse":[8,165],"worldwide":[9,166],"human":[10,82,167],"preferences":[11,107],"by":[12,108],"languages.":[13,113],"However,":[14],"those":[15],"could":[17],"suffer":[18],"from":[19],"bias":[20,119],"related":[21,120],"exceptional":[23,30,122],"social":[24,123],"circumstances.":[25],"Any":[26],"massive":[27],"event":[28],"promoting":[29],"editions":[31],"of":[32,40,72,81,106,118,143,148],"WP":[33,112],"can":[34],"be":[35],"defined":[36],"as":[37,160],"a":[38,47,66,127,161],"source":[39],"bias.":[41],"In":[42],"this":[43],"article,":[44],"we":[45,92,137],"follow":[46],"procedure":[48],"for":[49],"detecting":[50],"outliers.":[51,88],"Our":[52,63],"study":[53,78],"is":[54,69,125],"based":[55],"on":[56,134],"12":[57],"languages":[58],"and":[59],"13":[60],"different":[61,111],"categories.":[62],"methodology":[64],"defines":[65],"parameter,":[67],"which":[68],"language-dependent":[70],"instead":[71],"being":[73],"externally":[74],"fixed.":[75],"We":[76],"also":[77],"the":[79,95,104,116,141,144,149],"presence":[80],"cyclic":[83],"behavior":[84],"evaluate":[86],"apparent":[87],"After":[89],"our":[90,98],"analysis,":[91],"found":[93,138],"that":[94,139],"outliers":[96,152],"in":[97,140],"do":[100,153],"not":[101,154],"significantly":[102,155],"affect":[103,156],"analysis":[105,133],"categories":[109],"among":[110],"While":[114],"investigating":[115],"possibility":[117],"circumstances":[124],"always":[126],"safe":[128],"measure":[129],"before":[130],"doing":[131],"any":[132],"Big":[135],"Data,":[136],"case":[142],"first":[145],"ten":[146],"years":[147],"data-set,":[151],"using":[157],"digital":[162],"footprint":[163],"preferences.":[168]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}